BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment

• URL: http://arxiv.org/abs/2204.08332v1
• Date: Mon, 18 Apr 2022 14:23:10 GMT
• Title: BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
• Authors: Ziwei Luo, Youwei Li, Shen Cheng, Lei Yu, Qi Wu, Zhihong Wen, Haoqiang Fan, Jian Sun, Shuaicheng Liu
• Abstract summary: This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-resolution RAW bursts. We propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction. Our BSRT wins the championship in the NTIRE2022 Burst Super-Resolution Challenge.
• Score: 84.82352123245488
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-resolution RAW bursts. To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction. To achieve this goal, we propose a Pyramid Flow-Guided Deformable Convolution Network (Pyramid FG-DCN) and incorporate Swin Transformer Blocks and Groups as our main backbone. More specifically, we combine optical flows and deformable convolutions, hence our BSRT can handle misalignment and aggregate the potential texture information in multi-frames more efficiently. In addition, our Transformer-based structure can capture long-range dependency to further improve the performance. The evaluation on both synthetic and real-world tracks demonstrates that our approach achieves a new state-of-the-art in BurstSR task. Further, our BSRT wins the championship in the NTIRE2022 Burst Super-Resolution Challenge.

Related papers

• SwinFuSR: an image fusion-inspired model for RGB-guided thermal image super-resolution [0.16385815610837165]
  Super-resolution (SR) methods often struggle with thermal images due to lack of high-frequency details. Inspired by SwinFusion, we propose SwinFuSR, a guided SR architecture based on Swin transformers. Our method has few parameters and outperforms state of the art models in terms of Peak Signal to Noise Ratio (PSNR) and Structural SIMilarity (SSIM)
  arXiv  Detail & Related papers  (2024-04-22T19:01:18Z)
• Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures [17.517010701323823]
  Super-Resolution (SR) is a time-hallowed image processing problem. We introduce a fully-conversaal Generative Adrial Network (GAN)-based architecture for SR. We show that distinct convolutional features obtained at increasing depths of a GAN generator can be optimally combined by a set of learnable convex weights.
  arXiv  Detail & Related papers  (2024-04-09T13:19:43Z)
• Towards Real-World Burst Image Super-Resolution: Benchmark and Method [93.73429028287038]
  In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames. We also introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacement among images under real-world image degradation.
  arXiv  Detail & Related papers  (2023-09-09T14:11:37Z)
• RBSR: Efficient and Flexible Recurrent Network for Burst Super-Resolution [57.98314517861539]
  Burst super-resolution (BurstSR) aims at reconstructing a high-resolution (HR) image from a sequence of low-resolution (LR) and noisy images. In this paper, we suggest fusing cues frame-by-frame with an efficient and flexible recurrent network.
  arXiv  Detail & Related papers  (2023-06-30T12:14:13Z)
• Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network [101.53907377000445]
  Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. Existing methods result in the loss of middle-layer features due to activation functions. We propose a Feature Interaction Weighted Hybrid Network (FIWHN) to minimize the impact of intermediate feature loss on reconstruction quality.
  arXiv  Detail & Related papers  (2022-12-29T05:57:29Z)
• Learning Detail-Structure Alternative Optimization for Blind Super-Resolution [69.11604249813304]
  We propose an effective and kernel-free network, namely DSSR, which enables recurrent detail-structure alternative optimization without blur kernel prior incorporation for blind SR. In our DSSR, a detail-structure modulation module (DSMM) is built to exploit the interaction and collaboration of image details and structures. Our method achieves the state-of-the-art against existing methods.
  arXiv  Detail & Related papers  (2022-12-03T14:44:17Z)
• Single Image Super-Resolution Using Lightweight Networks Based on Swin Transformer [2.9649783577150837]
  We propose two lightweight models named as MSwinSR and UGSwinSR based on Swin Transformer. MSwinSR increases PSNR by $mathbf0.07dB$ compared with the state-of-the-art model SwinIR. The number of parameters can reduced by $mathbf30.68%$, and the calculation cost can reduced by $mathbf9.936%$.
  arXiv  Detail & Related papers  (2022-10-20T05:03:16Z)
• Bilateral Network with Channel Splitting Network and Transformer for Thermal Image Super-Resolution [8.754793353368255]
  This paper introduces the technical details of our submission to PBVS-2022 challenge designing a Bilateral Network with Channel Splitting Network and Transformer. The proposed method can achieve PSNR=33.64, SSIM=0.9263 for x4 and PSNR=21.08, SSIM=0.7803 for x2 in the PBVS-2022 challenge test dataset.
  arXiv  Detail & Related papers  (2022-06-24T02:48:15Z)
• Deep Burst Super-Resolution [165.90445859851448]
  We propose a novel architecture for the burst super-resolution task. Our network takes multiple noisy RAW images as input, and generates a denoised, super-resolved RGB image as output. In order to enable training and evaluation on real-world data, we additionally introduce the BurstSR dataset.
  arXiv  Detail & Related papers  (2021-01-26T18:57:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.